ML approaches for omic data analysis

Overview
Related items

This project focuses on developing and applying machine learning (ML) methodologies to analyze complex omic datasets, including genomics, transcriptomics, proteomics, and metabolomics. By leveraging advanced ML techniques, the project aims to uncover novel biological insights, identify biomarkers, and enhance our understanding of molecular mechanisms underlying various diseases. The initiative is a collaborative effort maintained by the Institute of Molecular Biology NAS RA (IMB), the Armenian Bioinformatics Institute (ABI), and the Interdisciplinary Centre for Bioinformatics (IZBI) at the University of Leipzig. These institutions bring together expertise in bioinformatics, molecular biology, and computational sciences to advance the field of omic data analysis.

Programme: Bioinformatics Tools for Analysis of Big Genomic Data

SEEK ID: https://armlifebank.am/projects/11

Funding codes:

22SC-BMBF-1C004

Public web page: Not specified

Organisms: No Organisms specified

ArmLifeBank PALs: No PALs for this Project

Project created: 7th Mar 2024

Related items

Showing 5 out of a possible 8 People Advanced People list for this Project with search and filtering

Arsen Arakelyan

Projects: Sex-specific differences in long-term gamma and simGCRsim-associated alterations in deferential gene expression in the heart tissue, Functional Genomics of Vine, Molecular Profiling of Cancer Metastases, Omics-Based Insights into Human Long-Term Exposure to Environmental Metals, Biological pathway activity analysis, ML approaches for omic data analysis, Tools for Telomere Biology, Mental disorders and aging brain, Armenian Wine Genome Program, Study of the molecular mechanisms of familial Mediterranean fever using genetic engineering and functional genomics, Molecular characterization of cancers with long-read RNA sequencing, Low dose radiation risks: present research and future perspectives

Institutions: Institute of Molecular Biology NAS RA, Armenian Bioinformatics Institute

https://orcid.org/0000-0002-6851-1056

Suren Davitavyan

Projects: ML approaches for omic data analysis

Institutions: Institute of Molecular Biology NAS RA

https://orcid.org/0000-0002-3414-5553

Meline Hakobyan

Projects: Tools for Telomere Biology, ML approaches for omic data analysis, Molecular characterization of cancers with long-read RNA sequencing

Institutions: Institute of Molecular Biology NAS RA

https://orcid.org/0000-0002-1089-0655

Siras Hakobyan

Projects: Biological pathway activity analysis, Sex-specific differences in long-term gamma and simGCRsim-associated alterations in deferential gene expression in the heart tissue, ML approaches for omic data analysis, Molecular characterization of cancers with long-read RNA sequencing

Institutions: Institute of Molecular Biology NAS RA

https://orcid.org/0000-0002-6875-2482

Expertise: Bioinformatics

Tools: Cytoscape, Genomics, Microarray analysis, Python, R, Single Cell analysis, Transcriptomics

Siras Hakobyan is currently a Junior Researcher and PhD student in the Research Group of Bioinformatics at the Institute of Molecular Biology NAS RA in Yerevan, Armenia. He received his Master's and Bachelor's degrees in Bioinformatics from Yerevan State University, completing his studies in 2018 and 2016. His PhD project focuses on pathway-centered analysis of high-throughput omics data, particularly examining pathway activity states in cancers based on pathway topology, gene expression, and ...

View all 8 People

Advanced Programmes list for this Project with search and filtering

Bioinformatics Tools for Analysis of Big Genomic Data

This Programme focuses on the development, implementation, and application of bioinformatics tools for the analysis of large-scale genomic datasets. It aims to facilitate the processing, integration, and interpretation of high-throughput sequencing data, including whole-genome, transcriptome, and epigenome analyses. The Programme encompasses computational approaches for variant discovery, gene expression profiling, network biology, and multi-omics data integration.

Projects: Biological pathway activity analysis, ML approaches for omic data analysis, Tools for Telomere Biology

Web page: Not specified

Advanced Institutions list for this Project with search and filtering

Armenian Bioinformatics Institute

Country: Armenia

City: Yerevan

Web page: https://www.abi.am

Institute of Molecular Biology NAS RA

Country: Armenia

City: Yerevan

Web page: https://molbiol.sci.am

Interdisciplinary Center for Bioinformatics (IZBI)

Country: Germany

City: Leipzig

Web page: https://www.izbi.uni-leipzig.de/

Russian-Armenian University

Country: Armenia

City: Yerevan

Web page: https://www.rau.am

Advanced Investigations list for this Project with search and filtering

Digital life sciences for genome-based healthcare

ML approaches for omic data analysis

DigitalLife aims at bringing together complementary Armenian and German competence of the project partners in three major areas: omics bioinformatics for health with single-cell omics resolution, the establishment of infrastructure for genomic data collection, analysis, and sharing, and the Research School offering a qualification program for young scientists. The research tasks include the development of pathway analysis and machine learning methods and software for single-cell omic data analysis, ...

Submitter: Arsen Arakelyan

Studies: No Studies

Assays: No Assays

Snapshots: No snapshots

Created: 14th Apr 2025 at 06:12

Advanced Data files list for this Project with search and filtering

Projection of high-dimensional genome-wide expression on SOM transcriptome landscapes: supplementary datasets

ML approaches for omic data analysis, Molecular characterization of cancers with long-read RNA sequencing

(Show All)

This is a supplementary dataset with raw data, scripts, and complete analysis results for the paper "Supervised projection of high-dimensional genome-wide expression on SOM transcriptome landscapes".

The archive contains three folders:

"Simdata" folder contains data, scripts, and results of performance evaluation of extension SOM and supervised SOM with simulated data.
"IBD" - folder contains data, scripts, and results of analysis of Inflammatory bowel disease datasets.
"BC" - folder ...

Creators: Maria Nikoghosyan, Suren Davitavyan, Hans Binder, Arsen Arakelyan

Submitter: Lana Karapetyan

Investigations: No Investigations

Studies: No Studies

Assays: No Assays

External Link

Created: 10th Jul 2025 at 10:26

Showing 5 out of a possible 7 Publications Advanced Publications list for this Project with search and filtering

Topology-aware pathway analysis of spatial transcriptomics

ML approaches for omic data analysis, Molecular characterization of cancers with long-read RNA sequencing

(Show All)

Abstract (Expand)

Spatial transcriptomics (ST) has transformed genomics by mapping gene expression onto intact tissue architecture, uncovering intricate cellular interactions that bulk and single-cell RNA sequencing … often overlook. Traditional ST workflows typically involve clustering spots, performing differential expression analyses, and annotating results via gene-set methods such as overrepresentation analysis (ORA) or gene set enrichment analysis (GSEA). More recent spatially-aware techniques extend these approaches by incorporating tissue organization into gene-set scoring. However, because they operate primarily at the level of individual genes, they may overlook the connectivity and topology of biological pathways, limiting their capacity to trace the propagation of signaling events within tissue regions. In this study, we address that gap by translating gene expression into pathway-level activity using the Pathway Signal Flow (PSF) algorithm. PSF integrates expression data with curated interaction networks to compute numeric activity scores for each branch of a biological pathway, producing a functionally annotated feature space that captures downstream signaling effects as branch-specific activity values. We applied PSF to two public 10x Genomics Visium datasets (human melanoma and mouse brain) and compared clustering based on PSF-derived pathway activities from 40 curated Kyoto Encyclopedia of Genes and Genomes (KEGG) signaling pathways and gene expression with standard Seurat Louvain clustering and spatially aware methods (Vesalius, spatialGE). We observed good correspondence between PSF-based and expression-based clustering when spatially aware clustering methods were used. This suggests that branch-level pathway activities can themselves drive clustering and pinpoint spatially deregulated processes. To assess cluster-specific functional annotation, we compared PSF results to conventional ORA (based on marker genes) and GSDensity (based on cluster-specific gene sets). PSF identified a broader set of significant pathways with substantial overlap with both ORA and GSDensity, providing increased sensitivity due to its branch-level resolution. We further demonstrated that PSF-derived activity values can be used to detect spatially deregulated pathway branches, yielding results comparable to those obtained with spatially aware gene set analysis approaches such as GSDensity and spatialGE. The availability of pathway topology and branch-specific information also enabled the identification of potential intercellular communication via ligand-receptor interactions between deregulated pathways in adjacent tumor regions. To support interactive exploration of results, we developed the PSF Spatial Browser, an R Shiny application for visualizing pathway activities, gene expression patterns, and deregulated pathway networks.

Authors: Siras Hakobyan, Maria Schmidt, H. Binder, A. Arakelyan

Date Published: 14th Aug 2025

Publication Type: Journal

DOI: 10.7717/peerj.19729

Citation:

Created: 18th Aug 2025 at 10:05

Temporal changes of gene expression in health, schizophrenia, bipolar disorder, and major depressive disorder.

Mental disorders and aging brain, ML approaches for omic data analysis

(Show All)

Abstract (Expand)

The molecular events underlying the development, manifestation, and course of schizophrenia, bipolar disorder, and major depressive disorder span from embryonic life to advanced age. However, little …

Authors: A. Arakelyan, S. Avagyan, A. Kurnosov, T. Mkrtchyan, G. Mkrtchyan, R. Zakharyan, K. R. Mayilyan, H. Binder

Date Published: 17th Feb 2024

Publication Type: Journal

PubMed ID: 38368435

Citation: Schizophrenia (Heidelb). 2024 Feb 17;10(1):19. doi: 10.1038/s41537-024-00443-7.

Created: 28th Apr 2024 at 14:09

Projection of High-Dimensional Genome-Wide Expression on SOM Transcriptome Landscapes

ML approaches for omic data analysis, Molecular characterization of cancers with long-read RNA sequencing

(Show All)

Abstract (Expand)

organizing maps portraying has been proven to be a powerful approach for analysis of transcriptomic, genomic, epigenetic, single-cell, and pathway-level data as well as for “multi-omic” integrative …

Authors: Maria Nikoghosyan, Henry Loeffler-Wirth, Suren Davidavyan, Hans Binder, Arsen Arakelyan

Date Published: 27th Dec 2021

Publication Type: Journal

DOI: 10.3390/biomedinformatics2010004

Citation: BioMedInformatics,2(1):62-76

Created: 7th Mar 2024 at 11:00

A Transcriptome-Wide Isoform Landscape of Melanocytic Nevi and Primary Melanomas Identifies Gene Isoforms Associated with Malignancy.

ML approaches for omic data analysis, Molecular characterization of cancers with long-read RNA sequencing

(Show All)

Abstract (Expand)

Genetic splice variants have become of central interest in recent years, as they play an important role in different cancers. Little is known about splice variants in melanoma. Here, we analyzed a …

Authors: Siras Hakobyan, Henry Loeffler-Wirth, Arsen Arakelyan, Hans Binder, Manfred Kunz

Date Published: 2nd Jul 2021

Publication Type: Journal

PubMed ID: 34281234

DOI: 10.3390/ijms22137165

Citation: International journal of molecular sciences,22(13)

Created: 10th Sep 2025 at 09:16

oposSOM-Browser: an interactive tool to explore omics data landscapes in health science.

ML approaches for omic data analysis

(Show All)

Abstract (Expand)

Background: oposSOM is a comprehensive, machine learning based open-source data analysis software combining functionalities such as diversity analyses, biomarker selection, function mining, and …

Authors: Henry Loeffler-Wirth, Jasmin Reikowski, Siras Hakobyan, Jonas Wagner, Hans Binder

Date Published: 19th Oct 2020

Publication Type: Journal

PubMed ID: 33076824

DOI: 10.1186/s12859-020-03806-w

Citation: BMC bioinformatics,21(1):465

Created: 10th Sep 2025 at 10:51

View all 7 Publications